Method for determining the amount of liquid carried by a target vehicle and unmanned vehicle

Abstract

The application provides a method for determining the amount of liquid carried by a target vehicle and an unmanned vehicle, and relates to the fields of computer vehicle control, intelligent auxiliary driving and smart mine. The method for determining the amount of liquid carried by the target vehicle comprises the following steps: receiving a working state of a target vehicle performing a working task, wherein the working state comprises target measurement information related to the amount of liquid stored in a liquid container, and the liquid container is arranged on the target vehicle; determining measurement information noise matched with the working state of the target vehicle; and fusing the measurement information noise and a measured liquid amount determined based on the target measurement information based on a Kalman filtering algorithm to obtain a target liquid amount used for controlling the target vehicle to perform a spraying working task or used for determining a remaining mileage of the target vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer vehicle control, the field of intelligent auxiliary driving, and the field of smart mine, and more particularly, to a method for determining a liquid amount carried by a target vehicle and an unmanned vehicle. BACKGROUND

[0002] With the rapid development of artificial intelligence technology, in operation scenarios such as mine operations, operation tasks can be performed based on unmanned operation vehicles to improve operation efficiency. For example, for mine operation scenarios, watering operations can be performed based on unmanned vehicles to avoid dust flying to affect air quality and operation safety. For another example, an unmanned vehicle can plan a driving path based on the remaining fuel liquid amount in the fuel tank, so that the unmanned vehicle can perform operation tasks such as cargo transportation according to the remaining fuel liquid amount.

[0003] In the process of implementing the concept of the present application, it is found that at least the following problems exist in the related art: In the process of performing a watering operation, it is difficult for an unmanned vehicle to accurately detect the remaining water amount in the water tank or the remaining fuel liquid amount in the fuel tank, resulting in low operation efficiency and prone to abnormal operation states such as unmanned vehicle empty driving. SUMMARY

[0004] Therefore, the present application provides a method for determining a liquid amount carried by a target vehicle, a method for controlling a vehicle, and an unmanned vehicle.

[0005] One aspect of the present application provides a method for determining a liquid amount carried by a target vehicle, comprising: receiving an operation state of a target vehicle performing an operation, the operation state comprising target measurement information related to a liquid amount of a liquid stored in a liquid container, the liquid container being arranged on the target vehicle; determining measurement information noise matched with the operation state of the target vehicle; and fusing the measurement information noise and a measured liquid amount determined based on the target measurement information based on a Kalman filtering algorithm to obtain a target liquid amount used for controlling the target vehicle to perform a spraying operation or used for determining a remaining mileage of the target vehicle.

[0006] Another aspect of the present application provides a method for controlling a vehicle, comprising: determining a target liquid amount related to a liquid container of a target vehicle according to the method for determining a liquid amount carried by a target vehicle provided in the embodiments of the present application, wherein the liquid container is arranged on the target vehicle; planning a target driving path for the target vehicle according to the target liquid amount to obtain the target driving path; and controlling the target vehicle to perform an operation task based on the target driving path.

[0007] Another aspect of the present application provides an unmanned vehicle, comprising: a liquid container configured to store liquid for a work task; a sensor configured to collect a work state, the work state comprising target measurement information related to a liquid amount of the liquid stored in the liquid container; and a processor configured to execute the method for determining the liquid amount carried by the target vehicle.

[0008] According to the embodiments of the present application, by selecting the measurement information noise matching the work state of the target vehicle based on the work state of the target vehicle, and fusing the measurement information noise and the measured liquid amount by the Kalman filtering algorithm, the measurement information noise adapting to the vehicle posture can be selected as the observation noise of the Kalman filtering algorithm based on the work state of the target vehicle, so that the measurement information noise can more accurately correct the measured liquid amount, thereby improving the detection accuracy of the liquid amount in the liquid container, so as to accurately adjust the execution parameters of the Kalman filtering algorithm by the work state to correct the measured liquid amount, thereby improving the actual estimation accuracy of the target liquid amount, and then the target vehicle can perform the work tasks such as spraying work and transportation work according to the accurate target liquid amount during the work process, so as to reduce the empty vehicle mileage and driving time, improve the work efficiency and work safety of the related work scene, meet the actual environmental protection demand and work efficiency demand. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other objects, features and advantages of the present application will become more apparent from the following description of the embodiments of the present application taken with reference to the accompanying drawings, in which:

[0010] Figure 1 An exemplary system architecture to which the method and apparatus for determining the liquid amount carried by the target vehicle according to the embodiments of the present application can be applied is shown.

[0011] Figure 2 A flowchart of the method for determining the liquid amount carried by the target vehicle according to the embodiments of the present application is shown.

[0012] Figure 3 An application scenario diagram of the method for determining the liquid amount carried by the target vehicle according to the embodiments of the present application is shown.

[0013] Figure 4 A flowchart of the method for controlling the vehicle according to the embodiments of the present application is shown.

[0014] Figure 5 A schematic diagram of the unmanned vehicle according to the embodiments of the present application is shown. DETAILED DESCRIPTION

[0015] Embodiments of the present application will be described herein below with reference to the drawings. It should be understood, however, that the description is merely exemplary and is not intended to limit the scope of the present application. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, that one or more embodiments can be practiced without these specific details. In other instances, well-known structures and techniques have not been described in detail in order to avoid unnecessarily obscuring the concepts of the present application.

[0016] The terminology used herein is for the purpose of describing specific embodiments only and is not intended to be limiting of the present application. As used herein, the term "includes" and tautological expressions thereof, such as "including," "includes," "include," "contains," "containing," and so on, mean the term "comprises."

[0017] All terms used herein, including technical and scientific terms, have the meanings commonly understood by one of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the specification, and should not be interpreted in an idealized or overly formal manner.

[0018] In the case of using expressions similar to "at least one of A, B, and C, etc.", it should generally be interpreted that the expression means "at least one of A, at least one of B, and at least one of C" (e.g., "a system having at least one of A, B, and C" should include but not be limited to a system having A alone, a system having B alone, a system having C alone, a system having both A and B, a system having both A and C, a system having both B and C, and / or a system having A, B, and C, etc.).

[0019] In the embodiments of the present application, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) comply with the relevant legal regulations, are used for legal purposes, and do not violate public order and good customs. In particular, necessary measures have been taken to prevent illegal access to user personal information data, and to maintain user personal information security, network security, and national security.

[0020] In the embodiments of the present application, the authorization or consent of the user is obtained before the user's personal information is acquired or collected.

[0021] In the process of executing the water spraying operation by the unmanned water vehicle, due to the large ups and downs of the driving road and the bumpy road surface, the vehicle attitude changes sharply. The water amount detected by the water tank container level sensor is difficult to accurately represent the actual water amount in the water tank, and thus it is difficult to plan the operation task of the unmanned water vehicle according to the remaining water amount in the water tank container, resulting in low operation efficiency and affecting the operation efficiency of mine operation scenes and the like.

[0022] Embodiments of the present application provide a method for determining the amount of liquid carried by a target vehicle, a method for controlling a vehicle, and an unmanned vehicle. The method for determining the amount of liquid carried by a target vehicle includes: receiving a working state of a target vehicle performing a working task, the working state including target measurement information related to the amount of liquid stored in a liquid container, the liquid container being arranged on the target vehicle; determining measurement information noise matched with the working state of the target vehicle; and fusing the measurement information noise and a measured amount of liquid determined based on the target measurement information based on a Kalman filtering algorithm to obtain a target amount of liquid for controlling the target vehicle to perform a spraying working task or for determining a remaining mileage of the target vehicle.

[0023] Figure 1 An exemplary system architecture to which the method and device for determining the amount of liquid carried by a target vehicle according to embodiments of the present application can be applied is shown. It should be noted that, Figure 1 the system architecture shown is only an example of the system architecture to which embodiments of the present application can be applied, to help those skilled in the art understand the technical content of the present application, but does not mean that embodiments of the present application cannot be applied to other devices, systems, environments or scenarios.

[0024] As Figure 1 shown, the system architecture 100 according to this embodiment can include a vehicle 101, a network 102 and a server 103. The network 102 is a medium for providing a communication link between the vehicle 101 and the server 103. The network 102 can include various connection types, such as wired and / or wireless communication links, etc.

[0025] A user can use the vehicle 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the vehicle 101, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients and / or social platform software, etc. (only as examples).

[0026] The vehicle 101 can be any type of vehicle capable of performing a spraying working task, for example, the vehicle 101 can be a water spraying vehicle, a pesticide spraying vehicle, a mineral transport vehicle, etc. Embodiments of the present application do not limit the specific type of the vehicle 101.

[0027] The server 103 can be a server providing various services, for example, a background management server providing support for websites browsed by users using the vehicle 101 (only as an example). The background management server can analyze and process received user requests and other data, and feed back the processing results (such as web pages, information, or data, etc. obtained or generated according to user requests) to terminal devices.

[0028] It should be noted that the method for determining the liquid amount carried by the target vehicle provided in the embodiments of the present application can be generally executed by the server 103. Accordingly, the liquid amount determination apparatus provided in the embodiments of the present application can be generally arranged in the server 103. The method for determining the liquid amount carried by the target vehicle provided in the embodiments of the present application can also be executed by a server or a server cluster different from the server 103 and capable of communicating with the vehicle 101 and / or the server 103. Accordingly, the liquid amount determination apparatus provided in the embodiments of the present application can also be arranged in a server or a server cluster different from the server 103 and capable of communicating with the vehicle 101 and / or the server 103. Alternatively, the method for determining the liquid amount carried by the target vehicle provided in the embodiments of the present application can also be executed by the vehicle 101, or can also be executed by another vehicle different from the vehicle 101. Accordingly, the liquid amount determination apparatus provided in the embodiments of the present application can also be arranged in the vehicle 101, or can also be arranged in another vehicle different from the vehicle 101.

[0029] It should be understood that the number of vehicles, networks and servers in the system is only illustrative. Any number of vehicles, networks and servers can be provided according to the implementation needs. Figure 1

[0030] A flowchart of the method for determining the liquid amount carried by the target vehicle according to the embodiments of the present application is shown. Figure 2 As shown in FIG. 2, the method for determining the liquid amount carried by the target vehicle includes operations S210-S230.

[0031] Figure 2 As shown in FIG. 2, the method for determining the liquid amount carried by the target vehicle includes operations S210-S230.

[0032] In operation S210, the working state of the target vehicle performing the working is received.

[0033] In operation S220, the measurement information noise matched with the working state of the target vehicle is determined.

[0034] In operation S230, the target liquid amount for controlling the target vehicle to perform the spraying working or for determining the remaining mileage of the target vehicle is obtained by fusing the measurement information noise and the measured liquid amount determined based on the target measurement information based on the Kalman filtering algorithm.

[0035] According to the embodiments of the present application, the liquid container is arranged on the target vehicle for performing the working task such as the spraying working, the transportation working, etc. The liquid container is any type of container such as the water tank, the fuel tank, etc. for storing the liquid. The liquid in the liquid container can be any type of liquid such as the water, the pesticide solution, the fuel, etc. The embodiments of the present application do not limit the specific types of the liquid and the liquid container.

[0036] ​According to embodiments of the present application, the working state includes target measurement information related to a liquid amount of the liquid stored in the liquid container. The target measurement information related to the liquid amount can include liquid level measurement information related to a liquid level of the liquid in the liquid container, or can also include injection flow measurement information related to performing a working task. The target measurement information can represent a working state of the target vehicle performing a working task such as a spraying work, a transportation work, etc. The liquid level measurement information can represent liquid level data measured by a device for measuring the liquid level of the liquid in the liquid container. For example, the liquid level measurement information can be liquid level data measured by a liquid level sensor arranged in the liquid container. The injection flow measurement information can represent measurement data of the liquid amount of the liquid flowing out of the liquid container in a preset period of time. For example, it can be measurement data of the liquid amount of fuel in a fuel tank container injected to an engine through a fuel injection nozzle. For another example, the injection flow measurement information can be measurement data of the liquid amount of water sprayed by the target vehicle into a working environment during the execution of the spraying work.

[0037] According to embodiments of the present application, the working state of the target vehicle can also include any state data related to the working task, such as a motion state of the target vehicle, a vehicle attitude, etc.

[0038] According to embodiments of the present application, the liquid in the liquid container can produce corresponding liquid form changes under different working state conditions, thereby negatively affecting the measurement accuracy of the liquid level measurement information. Further, in the case that the liquid form in the liquid container changes with the working state, the liquid form can form an irregular form such as a wavy surface, resulting in low measurement accuracy of the measured liquid amount based on the liquid level measurement information, and difficulty in representing the change of the actual liquid amount stored in the liquid container during the working process.

[0039] In some embodiments, the measured liquid amount can be determined based on the liquid level measurement information or the injection flow measurement information, for example, the measured liquid amount can be determined based on the product of the conversion coefficient and the liquid level measurement information. However, it is not limited thereto, and a plurality of liquid level measurement information can be obtained, and a plurality of initial measured liquid amounts corresponding to the plurality of liquid level measurement information can be weighted and averaged to obtain the measured liquid amount. The conversion coefficient can be designed based on the volume, shape, and other container parameters of the liquid container, and embodiments of the present application will not be repeated here.

[0040] According to embodiments of the present application, determining the measurement information noise matched with the working state can include querying a preset strategy information noise table based on the working state to obtain the measurement information noise having a mapping relationship with the working state. By establishing a mapping relationship between the preset working state and the preset measurement information noise, the corresponding measurement information noise can be determined according to the real-time detected working state.

[0041] In some embodiments, the measurement information noise can be taken as an observation noise R of a Kalman filtering mechanism, and the measurement liquid quantity is corrected based on the Kalman filtering mechanism according to the measurement information noise to obtain a more accurate target liquid quantity. The measurement liquid quantity of the target vehicle in different working state conditions is corrected by the measurement information noise corresponding to the plurality of working states, so that the target vehicle performing the spraying operation can detect the accurate target liquid quantity in real time according to the changing working state during the continuous spraying of the liquid.

[0042] In some embodiments, the target liquid quantity can be the remaining fuel liquid quantity during the working process of the target vehicle. Thus, the measurement liquid quantity of the target vehicle in different working state conditions can be corrected by the measurement information noise corresponding to the plurality of working states, so that the target vehicle can determine the remaining fuel quantity according to the target liquid quantity, and then plan the driving path according to the remaining fuel quantity, so that the target vehicle can perform the transportation operation and other operation tasks according to the more accurate remaining fuel quantity, avoid the termination of the operation task due to insufficient fuel quantity, and improve the operation efficiency of the target vehicle.

[0043] In some embodiments, the working state can include a speed value, an acceleration value, vehicle attitude information, and the like of the target vehicle, which can be acquired by a state acquisition device such as a speed sensor, an acceleration sensor, a gyroscope sensor, and the like arranged on the target vehicle. It should be noted that the motion state information such as the speed value, the acceleration value, and the vehicle attitude information of the target vehicle can be acquired based on a speed sensor, an acceleration sensor, and the like installed on the target vehicle.

[0044] In some embodiments, the working state of the target vehicle can be represented as any one of the preset conditions that the working state satisfies a preset stable working condition, a non-preset stable working condition, and a preset stable state condition.

[0045] According to embodiments of the present application, determining the measurement information noise matched with the working state of the target vehicle can include: determining at least one target measurement information to be corrected from a plurality of target measurement information related to the liquid quantity according to the working state of the target vehicle, and determining the measurement information noise corresponding to the target measurement information to be corrected.

[0046] According to embodiments of the present application, the target measurement information includes liquid level measurement information or injection flow measurement information. The plurality of target measurement information can include liquid level measurement information and injection flow measurement information. The measurement liquid level quantity determined according to the liquid level measurement information or the injection flow measurement information is difficult to accurately represent the actual liquid quantity in the liquid container at each time step.

[0047] It should be noted that the injection flow measurement information can represent measurement data of a flow meter measuring the amount of liquid flowing out of the liquid container. The injection flow measurement information can represent measurement data of the amount of water sprayed during the execution of the spraying operation, or measurement data of the amount of fuel injected from the fuel tank of the target vehicle to a fuel-consuming device such as an engine during the execution of the operation of the target vehicle.

[0048] In some embodiments, the liquid container is a fuel tank of the target vehicle, and the target liquid amount represents the amount of fuel remaining in the fuel tank. By processing the measurement information noise and the measurement liquid amount corresponding to the amount of fuel in the fuel tank based on the strategy information noise matched according to the operation state of the target vehicle, the target liquid amount representing the amount of fuel remaining in the fuel tank can be obtained based on the Kalman filtering algorithm, which can be more accurate. Thus, by improving the calculation accuracy of the amount of fuel remaining, the target vehicle can accurately plan a driving path based on the target liquid amount, so that the driving path is adapted to the remaining mileage of the target vehicle based on the amount of fuel remaining. In one example, determining at least one target measurement information to be corrected from a plurality of target measurement information related to the amount of liquid according to the operation state of the target vehicle can include, in a case where the operation state indicates that a preset stable operation condition is met, determining the liquid level measurement information as the target measurement information to be corrected, and determining the liquid level measurement noise as the measurement information noise according to the liquid level measurement information.

[0049] In one example, determining at least one target measurement information to be corrected from a plurality of target measurement information related to the amount of liquid according to the operation state of the target vehicle can include, in a case where the operation state indicates that a preset non-stable operation condition is met, determining the injection flow measurement information as the target measurement information to be corrected, and determining the flow measurement noise as the measurement information noise according to the injection flow measurement information. According to the embodiments of the present application, the preset stable operation condition can indicate that the target vehicle performs the injection operation in a stable motion state and a liquid injection state.

[0050] In some embodiments, the preset stable operation condition includes at least one of the following: the motion speed of the target vehicle meets a preset speed threshold; the vehicle attitude of the target vehicle meets a horizontal attitude condition; and the jolt acceleration corresponding to the target vehicle is less than a preset acceleration threshold.

[0051] For example, the motion speed of the target vehicle is 20 kilometers per hour, and the preset speed threshold can be a speed interval of 15 kilometers per hour to 25 kilometers per hour. The motion speed of the target vehicle meets the preset speed threshold.

[0052] For another example, the vehicle attitude of the target vehicle indicates that the angle difference between the vehicle body of the target vehicle and the horizontal reference line is 5°, and in a case where the preset attitude angle threshold is 0 to 10°, it is determined that the vehicle attitude of the target vehicle meets the horizontal attitude condition.

[0053] For another example, the jolt acceleration can be represented as a longitudinal acceleration of the target vehicle, and the jolt acceleration of the target vehicle is 1 m / s 2 , the preset jolt acceleration threshold is 0 to 1.5 m / s 2 , it can be determined that the jolt acceleration corresponding to the target vehicle is less than the preset acceleration threshold.

[0054] According to embodiments of the present application, the preset stable state condition can represent that the target vehicle is in a state close to a stop operation, for example, the preset stable state condition represents that the speed of the target vehicle satisfies a static speed condition, and the injection flow of the liquid in the liquid container of the target vehicle is less than a preset flow threshold. For example, the water flow of the water in the water tank container sprayed outward is less than the preset flow threshold, and for another example, the fuel flow of the fuel in the oil tank injected into the engine is less than the preset flow threshold.

[0055] In some embodiments, in the case that the operation state of the target vehicle does not satisfy the preset stable state condition and the preset stable operation condition, it can be determined that the operation state satisfies the non-preset stable operation condition. Thus, based on the specific preset condition satisfied by the operation state, the measurement noise information corresponding to the preset condition can be determined as the measurement noise of the Kalman filtering mechanism, so as to flexibly adjust the measurement noise of the Kalman filtering mechanism to accurately determine the accurate target liquid level under the operation state of each preset condition, and improve the detection accuracy of the liquid level.

[0056] In some embodiments, in the case that the operation state satisfies the preset stable operation condition, it can be determined that the measurement information noise corresponding to the operation state is the preset liquid level measurement noise R_level.

[0057] In some embodiments, the Kalman filtering algorithm fuses the measurement information noise and the measurement liquid quantity determined based on the target measurement information, including fusing the measurement information noise and the measurement liquid quantity based on the Kalman filtering mechanism, for example, in the case that the operation state represents that the target vehicle satisfies the preset stable operation condition, the tth target liquid quantity corresponding to the tth time step is determined based on the following operations: fusing the t-1th estimation variance and the preset process noise variance to obtain the tth prediction variance; performing Kalman gain calculation operation based on the tth prediction variance and the liquid level measurement noise corresponding to the preset stable operation condition to obtain the tth liquid level gain weight; and fusing the tth prediction liquid quantity and the tth measurement liquid quantity based on the tth liquid level gain weight to obtain the tth target liquid quantity.

[0058] According to embodiments of the present application, t is an integer greater than 1. The time step can represent a preset period or time, and the tth operation state corresponds to the tth time step. For example, the driving acceleration value collected in the tth time step can be the tth operation state.

[0059] According to embodiments of the present application, the t-1th estimated variance P_t-1 can be understood as an estimated variance determined based on the t-1th target liquid amount corresponding to the t-1th time step. The 1st estimated variance can be preset data determined through an initialization operation. It should be understood that the estimated variance can be a posteriori estimation covariance P + , representing an estimation error variance for the liquid amount.

[0060] In some embodiments, fusing the t-1th estimated variance and the preset process noise variance to obtain the tth prediction variance can include adding the t-1th estimated variance and the preset process noise variance to obtain the tth prediction variance. For example, the tth prediction variance can be represented based on formula (1).

[0061] P_pred_t = P_t-1 + Q (1).

[0062] wherein P_pred_t represents the tth prediction variance corresponding to the tth time step, the tth prediction variance can represent a priori estimation error covariance P - , P_t-1 is the t-1th estimated variance, Q is a preset process noise variance, and the process noise variance represents a process noise covariance matrix involved in the Kalman filtering algorithm.

[0063] In some embodiments, performing a Kalman gain calculation operation based on the tth prediction variance and a liquid level measurement noise corresponding to the preset stable operating condition to obtain a tth liquid level gain weight can include determining the tth liquid level gain weight corresponding to the preset stable operating condition based on formula (2).

[0064] K_level_t= P_pred_t / (P_pred_t + R_level) (2).

[0065] wherein K_level_t is the tth liquid level gain weight, the tth liquid level gain weight can represent a Kalman gain corresponding to the preset stable operating condition, which represents a weight for correcting the tth liquid level measurement information, and R_level represents a liquid level measurement noise corresponding to the preset stable operating condition, representing a sensor measurement error of the tth liquid level measurement information.

[0066] In some embodiments, fusing the tth predicted liquid amount and the tth measured liquid amount based on the tth liquid level gain weight to obtain the tth target liquid amount can include weighting and fusing the tth predicted liquid amount and the tth measured liquid amount based on the tth liquid level gain weight to obtain the tth target liquid amount. For example, the tth target liquid amount can be determined based on formula (3).

[0067] volume_t = volume_pred_t + K_level_t * (volume_from_level_t - volume_pred_t) (3).

[0068] wherein volume_t is the tth target liquid volume, volume_pred_t is the tth predicted liquid volume, which represents a predicted value determined based on a prediction equation, volume_from_level_t is the tth measured liquid volume, which represents a measured value for the liquid volume determined based on the tth level measurement information corresponding to the tth time step. Based on equation (3), the measured value for the liquid volume and the predicted value can be fused by weighting according to the tth level gain weight, so that the tth target liquid volume can accurately eliminate the measurement error of the sensor and the prediction error of the prediction equation, so that the tth target liquid volume can accurately represent the real target liquid volume in the liquid container corresponding to each time step under the working condition that the target vehicle stably performs the spraying operation.

[0069] In some embodiments, the tth measured liquid volume is determined based on the tth level measurement information corresponding to the tth time step, for example, the surface position of the liquid in the liquid container can be fitted based on a plurality of tth level measurement information collected by a plurality of level sensors arranged in the liquid container, and the tth measured liquid volume is calculated based on the surface position of the liquid and the shape and volume of the liquid container.

[0070] In some embodiments, the tth predicted liquid volume volume_pred_t is determined based on the t-1th target liquid volume volume_t-1 and the tth injection flow rate measurement information corresponding to the tth time step, and the working state includes the tth spraying flow rate measurement information.

[0071] For example, the tth predicted liquid volume volume_pred_t can be determined based on the following equation (4).

[0072] volume_pred_t = volume_t-1 + flow_rate_t * dt (4).

[0073] wherein volume_pred_t is the tth predicted liquid volume, volume_t-1 is the t-1th target liquid volume corresponding to the t-1th time step. dt is the duration corresponding to the time step, and flow_rate_t is the tth injection flow rate measurement information corresponding to the tth time step. The tth injection flow rate measurement information can represent liquid flow meter sensing information.

[0074] According to embodiments of the present application, the t-1th estimated variance is determined based on the t-1th predicted variance. For example, the t-1th estimated variance can be determined based on equation (5)

[0075] P_t-1= (1 - K_level_t-1) * P_pred_t-1 (5)。

[0076] wherein P_t-1 is the t-1 estimation variance, P_pred_t-1 is the t-1 prediction variance, and K_level_t-1 is the t-1 liquid level gain weight corresponding to the t-1 time step. Accordingly, the t estimation variance P_t is determined based on the t prediction variance P_pred_t and the t liquid level gain weight. The t estimation variance P_t, the t+1 working state corresponding to the t+1 time step, and the t+1 measured liquid amount can be used to calculate the t+1 target liquid amount corresponding to the t+1 time step.

[0077] Thus, the target liquid amount corresponding to each time step can be detected in the process of performing the spraying operation by the target vehicle in the case that the working state of the target vehicle meets the preset stable working condition. In the case that the liquid is fuel, the target vehicle can also determine the remaining fuel amount represented by the target liquid amount at multiple time steps. The target vehicle is planned for the working task more accurately and reasonably by the target liquid amount corresponding to multiple time steps, for example, the unmanned water truck can be planned for the working task execution parameters such as the driving trajectory and the spraying amount in the future time period based on the target liquid amount corresponding to each time step, so as to reduce the distance or time length of empty running of the unmanned water truck in the working site, and improve the working efficiency.

[0078] In some embodiments, the t liquid level measurement noise corresponding to the t time step is inversely proportional to the t acceleration value in the case that the working state meets the preset stable working condition, and the working state includes the t acceleration value corresponding to the t time step. The acceleration value includes any one of a longitudinal acceleration value representing the jolting degree of the target vehicle and a driving acceleration value representing the driving state of the target vehicle.

[0079] For example, in the case that the t longitudinal acceleration value is 1 m / s 2 , the t liquid level measurement noise can be determined as 3 m 3 by querying the preset liquid level measurement noise table. In the case that the t+1 longitudinal acceleration value is 1.3 m / s 2 , the t liquid level measurement noise can be determined as 2 m 3 by querying the preset liquid level measurement noise table. The t longitudinal acceleration value can represent the average value of the longitudinal acceleration of the target vehicle in the t time step.

[0080] According to the increase of the acceleration value of the target work vehicle, the noise value of the liquid level measurement noise can be reduced. When the work state meets the preset stable work condition, the correction degree of the liquid level measurement noise on the measured liquid level amount can be reduced by adjusting the noise value of the liquid level measurement noise in real time, so as to realize the measurement result of the trusted liquid level meter to improve the detection accuracy of the target liquid amount.

[0081] In some embodiments, determining the measurement information noise matched with the work state of the target vehicle can include: in response to the work state representing that the target vehicle meets the preset stable work condition, determining a first correction coefficient corresponding to the acceleration value in the work state; and updating the preset initial liquid level measurement noise according to the first correction coefficient to obtain the liquid level measurement noise.

[0082] In some embodiments, the first correction coefficient is inversely proportional to the acceleration value, which can be expressed as the first correction coefficient can be inversely proportional to the driving acceleration value of the target vehicle. The liquid level measurement noise is determined based on the product of the first correction coefficient and the initial liquid level measurement noise R_level. For example, the first correction coefficient k1=m1 / a, where a represents the driving acceleration value, k1 represents the first correction coefficient, and m1 represents a preset value. The liquid level measurement noise is k1*R_level_1, where R_level is the initial liquid level measurement noise. Thus, the target liquid amount can be calculated by converting formula (2) in the above embodiments to formula (6).

[0083] K_level_t= P_pred_t / (P_pred_t + k1*R_level_1) (6)。

[0084] The liquid level measurement noise is the measurement information noise matched with the work state meeting the preset stable work condition. Thus, the liquid level measurement noise can be reduced with the increase of the driving acceleration value when the work state of the target vehicle meets the preset stable work condition, so as to dynamically adjust the correction degree of the measured liquid level amount and the predicted liquid level amount according to the work state, and improve the detection accuracy of the target liquid amount.

[0085] In some embodiments, the fusing the measurement information noise and the measured liquid quantity determined based on the target measurement information can include fusing the measurement information noise and the measured liquid quantity determined based on the injection flow measurement information based on a Kalman filtering mechanism, for example, in a case where the job state characterization target vehicle satisfies the preset non-stable job condition, determining the jth target liquid quantity corresponding to the jth time step based on: fusing the j-1th estimated variance and a preset process noise variance to obtain a jth prediction variance; performing a Kalman gain calculation operation based on the jth prediction variance and a flow measurement noise corresponding to the preset non-stable job condition to obtain a jth flow gain weight; and fusing the jth injection flow measurement information and the jth predicted liquid quantity based on the jth flow gain weight to obtain the jth target liquid quantity.

[0086] In some embodiments, the fusing the j-1th estimated variance and the preset process noise variance to obtain the jth prediction variance can include adding the j-1th estimated variance and the preset process noise variance to obtain the jth prediction variance. For example, the jth prediction variance can be represented based on formula (7).

[0087] P_pred_j = P_j-1 + Q (7)

[0088] wherein, P_pred_j represents the jth prediction variance corresponding to the jth time step, the jth prediction variance can represent a priori estimated error covariance P - P_j-1 is the j-1th estimated variance, Q is the preset process noise variance, and the process noise variance represents a process noise covariance matrix involved in the Kalman filtering algorithm. It should be noted that j is an integer greater than 1, and j and i can be different integers.

[0089] In some embodiments, the performing the Kalman gain calculation operation based on the jth prediction variance and the flow measurement noise corresponding to the preset non-stable job condition to obtain the jth flow gain weight can include determining the jth flow gain weight corresponding to the preset non-stable job condition based on formula (8) as follows.

[0090] K_flow_j = P_pred_j / (P_pred_j + R_flow) (8).

[0091] wherein, K_flow_j is the jth flow gain weight, the jth flow gain weight can represent a Kalman gain corresponding to the preset non-stable job condition, indicating a weight for correcting the jth injection flow measurement information, and R_flow represents the flow measurement noise corresponding to the preset non-stable job condition, indicating a measurement error of the injection flow corresponding to the preset non-stable job condition within the time step.

[0092] In some embodiments, fusing the jth ejection flow rate measurement information and the jth predicted liquid volume based on the jth flow gain weight to obtain the jth target liquid volume can include determining the jth target liquid volume corresponding to the preset unstable operation condition according to the following formula (9).

[0093] volume_j= volume_pred_j + K_flow_j * (flow_rate_j * dt) (9)

[0094] wherein volume_j is the jth target liquid volume, volume_pred_j is the jth predicted liquid volume, which represents a predicted amount determined based on a prediction equation. flow_rate_j is the ejection flow rate sensor data corresponding to the jth time step, which represents the jth time step measurement ejection flow rate measurement information. dt is the time length of the time step. flow_rate_j * dt represents the ejection flow rate in the time step.

[0095] According to embodiments of the present disclosure, the jth predicted liquid volume is determined based on the jth-1 target liquid volume corresponding to the jth time step and the jth ejection flow rate measurement information,

[0096] For example, the jth predicted liquid volume volume_pred_j is determined based on the following formula (10).

[0097] volume_pred_j= volume_j-1+ flow_rate_j * dt (10)

[0098] wherein formula (9) can be determined based on formulas (10) and (11).

[0099] volume_j=volume_pred_j-K_flow_j*(volume_from_level_j- volume_pred_j)(11)

[0100] In the condition that the jth-1 target liquid volume volume_j-1 corresponding to the preset unstable operation condition and the jth measurement liquid volume volume_from_level_j are approximately equal, formula (9) can be determined in combination with formulas (10) and (11).

[0101] It should be noted that the flow measurement noise R_flow is related to the measurement error of the jth ejection flow rate measurement information, and the operation state includes the jth ejection flow rate measurement information corresponding to the jth time step, and the flow measurement noise is the measurement information noise matched with the operation state satisfying the preset unstable operation condition.

[0102] According to an embodiment of the present disclosure, the jth estimated variance is determined by fusing the jth flow gain weight and the jth predicted variance, for example, based on the following formula (12):

[0103] P_j = (1-K_flow_j) * P_pred_j (12)。

[0104] P_j is the jth estimated variance, P_pred_j is the jth predicted variance, and K_flow_j is the jth flow gain weight. The j-1th estimated variance is determined based on the j-1th predicted variance, for example, the j-1th estimated variance P_j-1 can be determined based on the formula (12). The jth estimated variance P_j, the j+1th working state corresponding to the j+1th time step, and the j+1th measured liquid amount can be used to calculate the j+1th target liquid amount corresponding to the j+1th time step under the preset unstable working condition.

[0105] In some embodiments, the jth flow measurement noise corresponding to the jth time step is inversely proportional to the jth acceleration value, and the working state includes the jth acceleration value corresponding to the jth time step. The working state includes the jth acceleration value corresponding to the jth time step. The acceleration value includes any one of a longitudinal acceleration value representing the degree of jolting of the target vehicle and a driving acceleration value representing the driving state of the target vehicle.

[0106] For example, when the jth longitudinal acceleration value is 6 m / s 2 , the jth flow measurement noise can be determined as 0.5 m 3 by querying the preset flow measurement noise table. When the j+1th longitudinal acceleration value is 6.3 m / s 2 , the jth flow measurement noise can be determined as 0.2 m 3 by querying the preset flow measurement noise table. The jth longitudinal acceleration value can represent the average value of the longitudinal acceleration of the target vehicle within the jth time step.

[0107] According to the embodiment of the present disclosure, the noise value of the flow measurement noise is reduced according to the increase of the acceleration value of the target working vehicle. In the case that the working state meets the preset unstable working condition, the degree of correction of the flow measurement noise on the measured liquid amount can be reduced by adjusting the noise value of the flow measurement noise in real time, so as to realize the detection accuracy of the target liquid amount by relying on the measurement result of the flow meter sensor.

[0108] In some embodiments, the determining the measurement information noise matched with the working state of the target vehicle can further include: in response to the working state representing that the target vehicle satisfies the preset non-stable working condition, determining a second correction coefficient corresponding to an acceleration value in the working state, wherein the second correction coefficient is inversely proportional to the acceleration value; and updating the preset initial flow measurement noise according to the second correction coefficient to obtain the flow measurement noise, which is the measurement information noise matched with the working state satisfying the preset non-stable working condition.

[0109] In some embodiments, the second correction coefficient is inversely proportional to the acceleration value, which can be expressed as k2 = n1 / a, where a represents the driving acceleration value, k2 represents the second correction coefficient, and n1 represents a preset value. The flow measurement noise is determined based on the product of the second correction coefficient and the initial flow measurement noise R_flow_1. For example, the flow measurement noise is k2*R_flow, where R_flow is the initial flow measurement noise. Thus, the target liquid level amount can be calculated by converting formula (8) in the above embodiments into formula (13).

[0110] K_flow_j = P_pred_t / (P_pred_t + k2*R_flow_1) (13)。

[0111] The flow measurement noise is the measurement information noise matched with the working state satisfying the preset non-stable working condition. Thus, in the case that the working state of the target vehicle satisfies the preset non-stable working condition, the flow measurement noise can be reduced with the increase of the driving acceleration value, so as to dynamically adjust the correction degree of the injection flow measurement value and the injection flow prediction value in the time step according to the working state, and improve the detection accuracy of the target liquid level amount. In the case that the liquid is fuel, the target vehicle can also determine the remaining fuel amount represented by the target liquid amount in multiple time steps to perform driving path planning, so as to improve the working continuity and stability. In the case that the liquid is water that needs to be sprayed, the target liquid amount corresponding to each time step can be used to perform spray amount planning and driving path planning for the target vehicle in real time, so as to improve the spray working efficiency of the target vehicle and reduce the mileage of empty driving.

[0112] In some embodiments, the liquid amount measurement method further includes: in response to the working state satisfying the preset stable state condition, performing liquid level amount detection based on the currently received liquid level measurement information to obtain a stable condition liquid level amount corresponding to the target vehicle satisfying the preset stable state condition.

[0113] According to embodiments of the present application, the preset stable state condition can represent that the target vehicle is in an approximately stationary reference state.

[0114] In some embodiments, the preset stable state condition represents at least one of the following: the target vehicle's speed is less than a preset speed threshold; the target vehicle's attitude satisfies the horizontal attitude condition; and the target vehicle's operational injection quantity is less than a preset injection quantity threshold.

[0115] For example, the target vehicle's speed being less than a preset speed threshold could be 0.1 m / s, which is less than the preset speed threshold of 0.5 m / s.

[0116] For example, if the target vehicle's operating spray volume is 0.01 cubic meters per hour, which is less than the preset spray volume threshold of 0.05 cubic meters per hour, then the target vehicle's operating spray volume is less than the preset spray volume threshold.

[0117] When the operating state meets the preset stable state conditions, the measured liquid volume at each time step can be determined based on the liquid level measurement information determined at each time step. Since the target vehicle is under the preset stable state conditions, the measured liquid level data characterized by the liquid level measurement information can be trusted, and the measured liquid volume at each time step can be determined as the target measured liquid volume at each time step.

[0118] In some embodiments, during the operation of the target vehicle, the operating state at different time steps meets different preset conditions. Therefore, based on the matching between the operating state and the preset conditions, the calculation mode for calculating the target liquid volume can be determined, thereby adjusting the calculation mode in real time to more accurately determine the target liquid volume at each time step.

[0119] Figure 3 An application scenario diagram is shown for a method for determining the amount of liquid carried by a target vehicle according to an embodiment of this application.

[0120] like Figure 3 As shown, the target vehicle performs spraying operations in different areas of the work scenario. In the first area 301, the target vehicle is stationary and preparing to move to the left to perform the spraying operation. In the first area 301, the target vehicle's speed and acceleration are 0, and the vehicle's attitude meets the horizontal attitude condition. At this time, the target vehicle's working state meets the preset stable state condition, and the target liquid volume is calculated based on Mode 1. Mode 1 can be, for example, based on multiple liquid level measurement information to perform liquid level detection, obtain the stable condition liquid level corresponding to the target vehicle that meets the preset stable state condition, and determine the stable condition liquid level as the target liquid level in the first area 301.

[0121] In the process that the target vehicle drives into the second region 302, the vehicle posture of the target vehicle does not satisfy the horizontal posture condition, and the acceleration value of the target vehicle is higher than the preset acceleration threshold. The working state of the target vehicle in the second region 302 satisfies the preset non-stable working condition, the flow measurement noise can be determined as the measurement information noise matched with the working state satisfying the preset non-stable working condition, and the target liquid amount corresponding to multiple time steps in the second region 302 of the target vehicle is calculated based on mode 2.

[0122] In the process that the target vehicle performs the spraying work in the second region 302, the flow measurement noise and the measurement liquid amount corresponding to multiple time steps are fused based on the Kalman filtering mechanism. For example, mode 2 can be used to determine the target liquid amount corresponding to each time step based on the above-mentioned formulas (7) to (12).

[0123] After the target vehicle drives from the second region 302 to the third region 303 to perform the spraying work, the vehicle posture of the target vehicle satisfies the horizontal posture condition, the movement speed of the target vehicle satisfies the preset speed threshold, the vehicle posture of the target vehicle satisfies the horizontal posture condition, and the jolt acceleration corresponding to the target vehicle is less than the preset acceleration threshold. It can be determined that the working state of the target vehicle performing the spraying work in the third region satisfies the preset stable working condition.

[0124] The target vehicle performing the spraying work in the third region 303 can determine the liquid level measurement noise as the measurement information noise based on mode 3, so as to fuse the liquid level measurement noise and the measurement liquid level amount according to the Kalman filtering mechanism to calculate the target liquid amount corresponding to multiple time steps of the target vehicle.

[0125] For example, mode 3 is used to obtain the ninth estimated variance P_9 calculated based on mode 2 corresponding to the ninth time step at the tenth time step, take the ninth estimated variance P_9 as the t-1 estimated variance P_t-1 shown in formula (1), and determine the target liquid amount corresponding to each time step of the target vehicle under the preset stable working condition based on formulas (1) to (5).

[0126] Therefore, the target vehicle can quickly switch the measurement information noise used in the Kalman filtering mechanism and the calculation mode used to calculate the target liquid amount under the condition that the working state of the target vehicle satisfies different preset conditions based on the example shown in formula (1). Figure 3 Thus, the target vehicle can accurately calculate the target liquid amount corresponding to each time step under the condition that the working state of the target vehicle satisfies any preset condition, so that the target vehicle can perform the spraying work more accurately and efficiently, and the working efficiency is improved.

[0127] In another embodiment of the present application, the target vehicle can switch the measurement information noise used in the Kalman filtering mechanism and the calculation mode used to calculate the target liquid amount based on the working state of the target vehicle. Figure 3The illustrated working state performs a spraying operation. The target liquid level amount corresponding to each time step in mode 2 can be determined based on formulas (7) to (13), and the target liquid amount of the target vehicle in mode 3 meeting the preset stable working condition can be determined based on formulas (1) to (6). In this way, the calculation accuracy of the target liquid amount can be improved by adjusting the liquid level measurement noise or the flow measurement noise in real time according to the acceleration value of the target vehicle at each time step.

[0128] In some embodiments, the liquid container is an oil tank of the target vehicle, and the target liquid amount represents the amount of fuel remaining in the oil tank. The target vehicle can determine the target liquid level amount corresponding to each time step in mode 2 based on formulas (7) to (13), and the target liquid amount of the target vehicle in mode 3 meeting the preset stable working condition can be determined based on formulas (1) to (6). In this way, the calculation accuracy of the remaining fuel amount can be improved by adjusting the liquid level measurement noise or the flow measurement noise in real time according to the acceleration value of the target vehicle at each time step, so that the target vehicle can accurately plan a driving path based on the target liquid amount, and the driving path can be adapted to the remaining mileage of the target vehicle based on the remaining fuel amount.

[0129] Based on the liquid level amount determination method provided by the embodiments of the present application, the embodiments of the present application further provide a method for controlling a vehicle.

[0130] Figure 4 A flowchart of the method for controlling a vehicle according to an embodiment of the present application is shown.

[0131] As Figure 4 shown, the method for controlling a vehicle includes operations S410 to S430.

[0132] In operation S410, the target liquid amount related to the liquid container of the target vehicle is determined according to the method for determining the liquid amount carried by the target vehicle provided by the embodiments of the present application.

[0133] In operation S420, the target vehicle is planned a driving path according to the target liquid amount, and a target driving path is obtained.

[0134] In operation S430, the target vehicle is controlled to perform a spraying operation based on the target driving path.

[0135] According to the embodiments of the present application, the liquid container is arranged on the target vehicle for performing the spraying operation.

[0136] According to an embodiment of the present application, the target vehicle is planned a driving path according to the target liquid amount, which can include determining the target liquid amount at each time step as the remaining liquid amount to be sprayed based on the target liquid amount corresponding to the current time step. The driving path is planned according to the target liquid amount and the preset liquid spraying amount, so that the target driving path is planned to enable the target vehicle to continuously perform spraying according to the preset liquid spraying amount during driving.

[0137] In some embodiments, the liquid container is an oil tank of the target vehicle, and the target liquid amount represents the remaining fuel amount in the oil tank. The target vehicle can determine the target liquid amount at each time step to represent the real-time remaining fuel amount in the oil tank based on the method provided by the embodiments of the present application. Thus, the calculation accuracy of the remaining fuel amount can be improved by adjusting the liquid level measurement noise or the flow measurement noise in real time according to the acceleration value of the target vehicle at each time step, so that the target vehicle can accurately plan a driving path based on the target liquid amount, and the driving path can be adapted to the remaining mileage of the target vehicle based on the remaining fuel amount.

[0138] In some embodiments, the target vehicle can be an unmanned vehicle having an unmanned function module, and the target vehicle can be automatically controlled to travel according to the target driving path based on the unmanned function module, so as to improve the work efficiency.

[0139] Based on the method for determining the liquid amount carried by the target vehicle and the method for controlling the vehicle provided by the above embodiments, the embodiments of the present application further provide an unmanned vehicle.

[0140] The unmanned vehicle includes a liquid container, a sensor and a processor.

[0141] The liquid container is configured to store liquid for a work task.

[0142] The sensor is configured to collect a work state, and the work state includes target measurement information related to the liquid amount of the liquid stored in the liquid container.

[0143] The processor is configured to execute the method for determining the liquid amount carried by the target vehicle provided by the embodiments of the present application.

[0144] In some examples, the sensor can include a liquid level measurement component installed on the liquid container. The sensor can also include a speed sensor or other components for collecting the motion state of the target vehicle.

[0145] Figure 5 A schematic diagram of an unmanned vehicle according to an embodiment of the present application is shown.

[0146] As shown in Figure 5 The unmanned vehicle 500 includes a liquid container 510, a liquid level measurement component 520 and a processor 530.

[0147] The liquid container 510 is configured to store liquid for a spraying operation.

[0148] The liquid level measuring component 520 is configured to collect liquid level measurement information related to the liquid stored in the liquid container 510.

[0149] The processor 530 is configured to perform the method for determining the target amount of liquid carried by the vehicle according to the embodiments of the present application.

[0150] In some embodiments, the liquid container can be a fuel tank of the unmanned vehicle, the target amount of liquid represents the amount of fuel remaining in the fuel tank, and the liquid level measurement component can represent measurement data of the liquid level of the fuel remaining in the fuel tank.

[0151] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions. The features of the various embodiments of the present application can be combined and / or combined in various ways without departing from the spirit and scope of the present application. In particular, the features of the various embodiments of the present application can be combined and / or combined in various ways without departing from the spirit and scope of the present application. All these combinations and / or combinations fall within the scope of the present application.

[0152] The embodiments of the present application are described above. However, these embodiments are only for illustrative purposes, and are not intended to limit the scope of the present application. Although each embodiment is described above separately, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Without departing from the scope of the present application, those skilled in the art can make various alternatives and modifications, which should fall within the scope of the present application.

Claims

1. A method for determining the amount of liquid carried by a target vehicle, characterized in that, The method comprises: receiving a job state of a target vehicle performing a job, the job state comprising target measurement information related to a liquid amount of a liquid stored in a liquid container arranged on the target vehicle; determining measurement information noise matched with the job state of the target vehicle, wherein, in a case where the job state indicates that a preset stable job condition is met, liquid level measurement information is determined as target measurement information to be corrected, and liquid level measurement noise is determined as the measurement information noise according to the liquid level measurement information; in a case where the job state indicates that a preset unstable job condition is met, injection flow measurement information is determined as target measurement information to be corrected, and flow measurement noise is determined as the measurement information noise according to the injection flow measurement information; fusing the measurement information noise and a measured liquid amount determined based on the target measurement information based on a Kalman filtering algorithm to obtain a target liquid amount for controlling the target vehicle to perform a spraying job or for determining a remaining mileage of the target vehicle.

2. The method of claim 1, wherein, In a case where the target measurement information related to the liquid amount comprises liquid level measurement information, the fusing the measurement information noise and the measured liquid amount determined based on the target measurement information based on the Kalman filtering algorithm comprises, in a case where the job state indicates that the target vehicle meets the preset stable job condition, determining a t th< target liquid amount corresponding to a t th< time step based on the following operations: fusing a t th< -1 estimated variance and a preset process noise variance to obtain a t th< prediction variance, t being an integer greater than 1; performing a Kalman gain calculation operation based on the t th< prediction variance and a liquid level measurement noise corresponding to the preset stable job condition to obtain a t th< liquid level gain weight, the liquid level measurement noise being the measurement information noise matched with the job state meeting the preset stable job condition; fusing a t th< prediction liquid amount and a t th< measured liquid amount based on the t th< liquid level gain weight to obtain the t th< target liquid amount, the t th< measured liquid amount being determined based on t th< liquid level measurement information corresponding to the t th< time step, the t th< prediction liquid amount being determined based on a t th< -1 target liquid amount and t th< injection flow measurement information corresponding to the t th< time step, the job state comprising the t th< injection flow measurement information, the t th< -1 estimated variance being determined based on a t th< -1 prediction variance.

3. The method of claim 2, wherein, The preset stable job condition comprises at least one of the following: a motion speed of the target vehicle meets a preset speed threshold; a vehicle posture of the target vehicle meets a horizontal posture condition; a jolt acceleration corresponding to the target vehicle is less than a preset acceleration threshold.

4. The method of claim 2, wherein, The t th< liquid level measurement noise corresponding to the t th< time step is inversely proportional to a t th< acceleration value, the job state comprising the t th< acceleration value corresponding to the t th< time step.

5. The method according to claim 1 or 2, characterized in that, In a case where the target measurement information comprises injection flow measurement information, the fusing the measurement information noise and the measured liquid amount determined based on the target measurement information based on the Kalman filtering algorithm comprises, in a case where the job state indicates that the target vehicle meets the preset unstable job condition, determining a j th< target liquid amount corresponding to a j th< time step based on the following operations: fusing the jth-1 estimated variance with a preset process noise variance to obtain a jth predicted variance, j being an integer greater than 1; performing a Kalman gain calculation operation based on the jth predicted variance and a flow measurement noise corresponding to the preset unstable operation condition to obtain a jth flow gain weight, the flow measurement noise being related to a measurement error of jth injection flow measurement information, the operation state including the jth injection flow measurement information corresponding to a jth time step, the flow measurement noise being measurement information noise matched with the operation state satisfying the preset unstable operation condition; fusing the jth injection flow measurement information and the jth predicted liquid amount based on the jth flow gain weight to obtain a jth target liquid amount, wherein the jth predicted liquid amount is determined based on a jth-1 target liquid amount corresponding to the jth time step and the jth injection flow measurement information, and the jth estimated variance is determined by fusing the jth flow gain weight and the jth predicted variance, the jth-1 estimated variance being determined based on the jth-1 predicted variance.

6. The method of claim 5, wherein, The jth flow measurement noise corresponding to the jth time step is inversely proportional to the jth acceleration value, and the operation state includes the jth acceleration value corresponding to the jth time step.

7. The method of claim 1, wherein, Further comprising: in response to the operation state satisfying a preset stable state condition, performing liquid level amount detection based on currently received liquid level measurement information to obtain a stable condition liquid level amount corresponding to a target vehicle satisfying the preset stable state condition, wherein the preset stable state condition represents at least one of the following: a driving speed of the target vehicle is less than a preset speed threshold; a vehicle posture of the target vehicle satisfies a horizontal posture condition; an operation injection amount of the target vehicle is less than a preset injection amount threshold.

8. The method of claim 1, wherein, determining measurement information noise matched with the operation state of the target vehicle further comprises: in response to the operation state representing that the target vehicle satisfies a preset stable operation condition, determining a first correction coefficient corresponding to an acceleration value in the operation state, wherein the first correction coefficient is inversely proportional to the acceleration value; updating a preset initial liquid level measurement noise according to the first correction coefficient to obtain a liquid level measurement noise, the liquid level measurement noise being measurement information noise matched with the operation state satisfying the preset stable operation condition; and / or determining measurement information noise matched with the operation state of the target vehicle further comprises: in response to the operation state representing that the target vehicle satisfies a preset unstable operation condition, determining a second correction coefficient corresponding to an acceleration value in the operation state, wherein the second correction coefficient is inversely proportional to the acceleration value; updating a preset initial flow measurement noise according to the second correction coefficient to obtain a flow measurement noise, the flow measurement noise being measurement information noise matched with the operation state satisfying the preset unstable operation condition.

9. An unmanned vehicle, characterized in that comprising: a liquid container configured to store liquid for performing an operation task; a sensor configured to collect an operation state, the operation state including target measurement information related to a liquid amount of the liquid stored in the liquid container; a processor configured to perform the method according to any one of claims 1 to 8.

Images